Kyungjae Lee

Associate Professor@Korea University·韩国·OpenReview

研究方向

heavy-tailed bandits · multi-armed bandits · reinforcement learning · safe reinforcement learning · distributional reinforcement learning · statistical learning theory · domain generalization

4.0

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

ICML 2025Poster

5.4

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

ICLR 2025Rejected

三作

-1

Time to Truncate Trajectory: Stochastic Retrace for Multi-step Off-policy Reinforcement Learning

合作者 (11)

Kyungjae Lee

Stochastic Truncation for Multi-Step Off-Policy RL

Policy-labeled Preference Learning: Is Preference Enough for RLHF?

Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

Time to Truncate Trajectory: Stochastic Retrace for Multi-step Off-policy Reinforcement Learning